Contextualizing Argument Quality Assessment with Relevant Knowledge

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Deshpande, Darshan, Sourati, Zhivar, Ilievski, Filip, Morstatter, Fred
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909225608806400
author Deshpande, Darshan
Sourati, Zhivar
Ilievski, Filip
Morstatter, Fred
author_facet Deshpande, Darshan
Sourati, Zhivar
Ilievski, Filip
Morstatter, Fred
contents Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing computational methods analyze their quality in isolation, which affects their accuracy and generalizability. We propose SPARK: a novel method for scoring argument quality based on contextualization via relevant knowledge. We devise four augmentations that leverage large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument. SPARK uses a dual-encoder Transformer architecture to enable the original argument and its augmentation to be considered jointly. Our experiments in both in-domain and zero-shot setups show that SPARK consistently outperforms existing techniques across multiple metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2305_12280
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Contextualizing Argument Quality Assessment with Relevant Knowledge
Deshpande, Darshan
Sourati, Zhivar
Ilievski, Filip
Morstatter, Fred
Computation and Language
Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing computational methods analyze their quality in isolation, which affects their accuracy and generalizability. We propose SPARK: a novel method for scoring argument quality based on contextualization via relevant knowledge. We devise four augmentations that leverage large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument. SPARK uses a dual-encoder Transformer architecture to enable the original argument and its augmentation to be considered jointly. Our experiments in both in-domain and zero-shot setups show that SPARK consistently outperforms existing techniques across multiple metrics.
title Contextualizing Argument Quality Assessment with Relevant Knowledge
topic Computation and Language
url https://arxiv.org/abs/2305.12280